Spoken Language Identification (v0.2)

About this version

• Submitter: keighrim
• Submission Time: 2025-11-06T10:31:10+00:00
• Prebuilt Container Image: ghcr.io/clamsproject/app-spoken-lid:v0.2

• Release Notes

  updated to the new whisper (python dependecy compatibilty)

About this app (See raw metadata.json)

Chunk-level language ID over audio based on OpenAI Whisper

• App ID: http://apps.clams.ai/spoken-lid/v0.2
• App License: Apache 2.0
• Source Repository: https://github.com/clamsproject/app-spoken-lid (source tree of the submitted version)
• Analyzer Version: v20250625
• Analyzer License: MIT

Inputs

(Note: “*” as a property value means that the property is required but can be any value.)

One of the following is required: [

• http://mmif.clams.ai/vocabulary/AudioDocument/v1 (required) (of any properties)

• http://mmif.clams.ai/vocabulary/VideoDocument/v1 (required) (of any properties)

]

Configurable Parameters

(Note: Multivalued means the parameter can have one or more values.)

• model: optional, defaults to tiny

  • Type: string
  • Multivalued: False
  • Choices: tiny, base, small, medium, large, turbo

  Whisper model size

• chunk: optional, defaults to 30

  • Type: number
  • Multivalued: False

  chunk/window length in seconds

• top: optional, defaults to 3

  • Type: integer
  • Multivalued: False

  top-k language scores

• batchSize: optional, defaults to 1

  • Type: integer
  • Multivalued: False

  number of windows processed in a batch

• pretty: optional, defaults to false

  • Type: boolean
  • Multivalued: False
  • Choices: false, true

  The JSON body of the HTTP response will be re-formatted with 2-space indentation

• runningTime: optional, defaults to false

  • Type: boolean
  • Multivalued: False
  • Choices: false, true

  The running time of the app will be recorded in the view metadata

• hwFetch: optional, defaults to false

  • Type: boolean
  • Multivalued: False
  • Choices: false, true

  The hardware information (architecture, GPU and vRAM) will be recorded in the view metadata

Outputs

(Note: “*” as a property value means that the property is required but can be any value.)

(Note: Not all output annotations are always generated.)

• http://mmif.clams.ai/vocabulary/TimeFrame/v6
  • timeUnit = “seconds”
  • labalSet = “https://raw.githubusercontent.com/openai/whisper/refs/tags/v20250625/whisper/tokenizer.py”